{"id":"https://openalex.org/W2126075801","doi":"https://doi.org/10.1145/2063576.2063592","title":"Discovering URLs through user feedback","display_name":"Discovering URLs through user feedback","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2126075801","doi":"https://doi.org/10.1145/2063576.2063592","mag":"2126075801"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101581308","display_name":"Xiao Bai","orcid":"https://orcid.org/0000-0002-7491-2454"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Xiao Bai","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"B. Barla Cambazoglu","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039618797","display_name":"Flavio Junqueira","orcid":"https://orcid.org/0009-0000-6789-5505"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Flavio P. Junqueira","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101581308"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":5.1727,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95454405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.950657308101654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7811006307601929},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.741446852684021},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6903889179229736},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.6509150862693787},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.6067940592765808},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5896238088607788},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.552030086517334},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5355095267295837},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3712334632873535}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.950657308101654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811006307601929},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.741446852684021},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6903889179229736},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.6509150862693787},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.6067940592765808},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5896238088607788},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.552030086517334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5355095267295837},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3712334632873535},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1566984846","https://openalex.org/W1609708070","https://openalex.org/W1613836731","https://openalex.org/W1904710255","https://openalex.org/W1985835043","https://openalex.org/W1989813732","https://openalex.org/W2000273502","https://openalex.org/W2007687650","https://openalex.org/W2018928332","https://openalex.org/W2029341294","https://openalex.org/W2030453570","https://openalex.org/W2030649419","https://openalex.org/W2038378248","https://openalex.org/W2053049304","https://openalex.org/W2059166475","https://openalex.org/W2081948558","https://openalex.org/W2094930182","https://openalex.org/W2096227190","https://openalex.org/W2103545802","https://openalex.org/W2107252390","https://openalex.org/W2110034127","https://openalex.org/W2119012894","https://openalex.org/W2124916819","https://openalex.org/W2134131174","https://openalex.org/W2145990704","https://openalex.org/W2148738951","https://openalex.org/W2148931201","https://openalex.org/W2151592910","https://openalex.org/W2151932833","https://openalex.org/W2157748587","https://openalex.org/W2163941332","https://openalex.org/W2164542999","https://openalex.org/W2169263924","https://openalex.org/W2170188121","https://openalex.org/W2295141584","https://openalex.org/W2911388033","https://openalex.org/W6674017165"],"related_works":["https://openalex.org/W2095543197","https://openalex.org/W2417265363","https://openalex.org/W2402678663","https://openalex.org/W2377634017","https://openalex.org/W3201526811","https://openalex.org/W2379145789","https://openalex.org/W2610451498","https://openalex.org/W1994958611","https://openalex.org/W4200125296","https://openalex.org/W2277785728"],"abstract_inverted_index":{"Search":[0],"engines":[1,205],"rely":[2],"upon":[3],"crawling":[4],"to":[5,56,98,105,133],"build":[6],"their":[7,143],"Web":[8,12,27,36,82,104,150],"page":[9,53],"collections.":[10],"A":[11],"crawler":[13,60,97,184],"typically":[14],"discovers":[15],"new":[16,123],"URLs":[17,42,136,159,179],"by":[18,24,140,148,168,182,193],"following":[19],"the":[20,30,35,63,71,89,96,103,128,135,169,183,187,213],"link":[21],"structure":[22],"induced":[23],"links":[25],"on":[26,34,49,111],"pages.":[28],"As":[29],"number":[31],"of":[32,73,131,158,178,198,215],"documents":[33,101],"is":[37,54,86,201],"large,":[38],"discovering":[39],"newly":[40],"created":[41],"may":[43,61],"take":[44],"arbitrarily":[45],"long,":[46],"and":[47],"depending":[48],"how":[50],"a":[51,59,75,81,112,119,155,175],"given":[52],"connected":[55],"others,":[57],"such":[58],"miss":[62],"pages":[64],"altogether.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"evaluate":[70],"benefits":[72],"integrating":[74],"passive":[76,87,219],"URL":[77,124,220],"discovery":[78],"mechanism":[79,85,113],"into":[80],"crawler.":[83,151,170],"This":[84],"in":[88,162,212],"sense":[90],"that":[91,114,137,154,160,174,202],"it":[92],"does":[93],"not":[94,146,166],"require":[95],"actively":[99],"fetch":[100],"from":[102,209],"discover":[106],"URLs.":[107],"We":[108,126,152,171],"focus":[109],"here":[110],"uses":[115],"toolbar":[116,129,163,216],"data":[117],"as":[118],"representative":[120],"source":[121],"for":[122,218],"discovery.":[125,221],"use":[127],"logs":[130,164,217],"Yahoo!":[132,149],"characterize":[134],"are":[138,165,180,190],"accessed":[139,192],"users":[141],"via":[142],"browsers,":[144],"but":[145],"discovered":[147,167,181],"show":[153],"high":[156],"fraction":[157,177],"appear":[161],"also":[172],"reveal":[173],"certain":[176],"later":[185],"than":[186],"time":[188],"they":[189],"first":[191],"users.":[194],"One":[195],"important":[196],"conclusion":[197],"our":[199],"work":[200],"web":[203],"search":[204],"can":[206],"highly":[207],"benefit":[208],"user":[210],"feedback":[211],"form":[214]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
